a version of rancid-fe that monitors child processes and kills them after 300 seconds

rancid-fe

#! /usr/bin/perl5
##
## $Id: rancid-fe.in 2296 2011-04-27 18:18:56Z heas $
##
## rancid 2.3.8
## Copyright (c) 1997-2008 by Terrapin Communications, Inc.
## All rights reserved.
##
## This code is derived from software contributed to and maintained by
## Terrapin Communications, Inc. by Henry Kilmer, John Heasley, Andrew Partan,
## Pete Whiting, Austin Schutz, and Andrew Fort.
##
## Redistribution and use in source and binary forms, with or without
## modification, are permitted provided that the following conditions
## are met:
## 1. Redistributions of source code must retain the above copyright
##    notice, this list of conditions and the following disclaimer.
## 2. Redistributions in binary form must reproduce the above copyright
##    notice, this list of conditions and the following disclaimer in the
##    documentation and/or other materials provided with the distribution.
## 3. All advertising materials mentioning features or use of this software
##    must display the following acknowledgement:
##        This product includes software developed by Terrapin Communications,
##        Inc. and its contributors for RANCID.
## 4. Neither the name of Terrapin Communications, Inc. nor the names of its
##    contributors may be used to endorse or promote products derived from
##    this software without specific prior written permission.
## 5. It is requested that non-binding fixes and modifications be contributed
##    back to Terrapin Communications, Inc.
##
## THIS SOFTWARE IS PROVIDED BY Terrapin Communications, INC. AND CONTRIBUTORS
## ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
## TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
## PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COMPANY OR CONTRIBUTORS
## BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
## CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
## SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
## INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
## CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
## ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
## POSSIBILITY OF SUCH DAMAGE.
#
#  rancid-FE - front-end to rancid/jrancid/etc. for use with par.
#
# usage: rancid-fe <router>:<vendor>
#

require 5;
use strict;

my ($router, $vendor) = split('\:', $ARGV[0]);
$vendor =~ tr/[A-Z]/[a-z]/;

# doesn't cover grandchildren, and expect processes are going to 100% cpu once their parent dies.
# looking at Proc::Killfam to fix this
sub kill_everyone {
    my $pid = shift;

    printf(STDERR "Had to run kill_everyone on $router\n");

    kill(-11, -$pid);
    kill(-11, $pid);
    sleep(1);
    kill(-9, $pid);
    die "TIMEOUT!";
}

sub forkexec {
    my $program = shift;
    my $pid = fork();

    if ($pid > 0){
        eval{
            local $SIG{ALRM} = sub { kill_everyone($pid) };
            alarm 300;
            waitpid($pid, 0);
            alarm 0;
            exit 0;
        };
    }
    elsif ($pid == 0){
        setpgrp;
        exec($program);
        exit(0);
    }
}


my %vendortable = (
    'agm'               => 'agmrancid',
    'alteon'            => 'arancid',
    'arista'            => 'arrancid',
    'avocent'           => 'avorancid',
    'baynet'            => 'brancid',
    'cat5'              => 'cat5rancid',
    'cisco'             => 'rancid',
    'cisco-nx'          => 'nxrancid',
    'cisco-xr'          => 'xrrancid',
    'css'               => 'cssrancid',
    'casa'      => 'casarancid',
    'enterasys'         => 'rivrancid',
    'erx'               => 'jerancid',
    'extreme'           => 'xrancid',
    'ezt3'              => 'erancid',
    'f5'                => 'f5rancid',
    'force10'           => 'f10rancid',
    'fortigate'         => 'fnrancid',
    'foundry'           => 'francid',
    'hitachi'           => 'htrancid',
    'hp'                => 'hrancid',
    'juniper'           => 'jrancid',
    'mikrotik'          => 'mtrancid',
    'mrtd'              => 'mrancid',
    'mrv'               => 'mrvrancid',
    'netopia'           => 'trancid',
    'netscaler'         => 'nsrancid',
    'netscreen'         => 'nrancid',
    'procket'           => 'prancid',
    'redback'           => 'rrancid',
    'riverstone'        => 'rivrancid',
    'smc'               => 'srancid',
    'tnt'               => 'tntrancid',
    'zebra'             => 'zrancid',
    'trango'    => 'trango_rancid',
    'hatteras'    => 'hatrancid',
    'dlink'    => 'drancid',
    'allied_telesyn'    => 'atrancid',
    'test'              => 'testrancid',

);

if ($vendortable{$vendor} eq "") {
    printf(STDERR "unknown router manufacturer for $router: $vendor\n");
    exit(-1);
} else {
    forkexec($vendortable{$vendor} . " $router");
}

printf(STDERR "exec failed router manufacturer $vendor: $!\n");
exit(-1);

This is used by my company because we've got some routers behind some unreliable links. I prefer to back them up when we can, but ssh/telnet can hang in ways that it's internal timeout won't kill it. Expects timeout also can't kill it, so clogin never dies. Rancid in turn never dies.

The safest place to watch over the entire stack was in rancid-fe, so I changed the code there to fork/exec with SIGALRM.